Self-Reflection in Language Model Agents

Follow this topic Ask about this topic

Latest papers

36 papers7 papers in the last four weeks, up 75% on the four weeks before. 0.0% of all new papers.

Oct 19, 2026

AllPath: Layered Verification for a Deployed, Self-Revising LLM Trading Agent under Human-Gated and Autonomous Regimes

LLM trading agents are evaluated almost exclusively in backtests and autonomous benchmark harnesses. Deployment, where actions are irreversible, raises a different question: who verifies the agent's actions, and which failures can each verifier structurally catch? We report on AllPath, a personal LLM trading agent deployed against a live paper-brokerage account. The system watches positions through a deterministic rules engine, and each night it reviews its own day and proposes revisions to its own trading strategies. Verification is split across three layers. Code verifies what must not depend on judgment: deterministic gates enforce risk limits and block any strategy revision that fails an integrity check. The agent verifies itself within fixed bounds: its nightly review has an iteration cap and no tools that can act. A human verifies judgment, through approval screens that show the current state of each proposal. We also compared two verification policies for the agent's self-revisions on the live system: two and a half weeks with every self-revision human-gated, then five weeks with reflection revisions auto-applied behind the same code gates, while the operator's chat channel stayed human-gated throughout. Each layer caught a different kind of failure. The code gates rejected no proposal; their role was keeping revisions consistent. The human rejected two proposals that passed every code check, both over a disagreement about the market, and later removed 11 of the 19 rules the agent had added on its own, at a median lag of eight days. The most instructive production incidents, such as strategies silently left unmonitored, passed every gate; the operator found them by hand, and the fix each time was an interface change that makes the condition visible. We contribute the layered architecture, the two-regime account, and a production incident taxonomy, none observable in a backtest.

Tian Zhang, Meng Li

Independent Researcher USA

LLM Agent Verification LLM Agents LLM Agent Reliability AI Agent Monitoring Runtime Enforcement for AI Agents Self-Reflection in Language Model Agents

Oct 19, 2026

CoMem: Learning to Anticipate Failures from Retrieved Experience

Reflection lets LLM agents improve from their own attempts, but the memory it builds is local to a single task, so an agent reflecting on its own tends to revisit the same explanation for failure. Cross-task reflective memory addresses this in two forms: retrieved memory keeps past experience explicit and looks up related cases, which is specific but bounded by the bank, and parametric memory internalizes experience into parameters, which generalizes but is grounded in nothing beyond the task description. When both are used, existing agents combine them additively, feeding their outputs to the solver side by side, so retrieved experience never changes what the learned memory produces. We introduce CoMem (Compounding Memory), which makes retrieved experience an input to the learned memory itself, at training and at inference. The agent builds a bank of its own successful and failed reflections, learns from retrieved cases to write failure hypotheses, candidate explanations of how an attempt is likely to go wrong, and at test time reasons from newly retrieved cases to guide each attempt. Varying the retrieved cases gives the memory different perspectives, yielding reflective diversity that is not merely sampled but also grounded in retrieved experience. Across two backbones and five benchmarks in math, code, and multi-hop QA, CoMem achieves strong overall performance. Additional evaluations show that it generalizes to out-of-distribution tasks and enables smaller models to provide effective guidance to stronger solvers.

Yun Shen, Ming Shen, Tianjun Yao

The Ohio State University · Shenzhen Loop Area Institute · Shanghai Jiaotong University

Memory-Augmented Language Model Agents Self-Reflection in Language Model Agents LLM Agent Reliability Retrieval-Augmented Reasoning

Oct 19, 2026

InteractAgent: Agentic Human Motion Interaction with Memory-Augmented Reflection

Long-horizon human-scene interaction requires coordinated spatial reasoning, physical feasibility, and the ability to recover from compounding execution errors. Text-driven motion models are largely scene-agnostic and lack closed-loop correction, while geometry-conditioned approaches depend on paired scene-motion training or explicit 3D preprocessing that limits generalization to novel layouts and open-vocabulary goals. We present InteractAgent, an agentic multimodal LLM system for long-horizon human-scene interaction that plans, executes, observes, and reflects in a closed loop, using a single MLLM as both planner and evaluator and a frozen MotionLLM as the executor. InteractAgent integrates Online Observation for step-wise recovery decisions (continue/redo/replan) and Memory-Augmented Reflection for multi-round plan refinement with adaptive stopping. On UniHSI, InteractAgent improves task success and reduces penetration compared with training-free baselines. Code: https://github.com/AIGeeksGroup/InteractAgent.

Tao Zhang, Senhe Zhang, Zeyu Zhang +2

AI Geeks · UNSW Sydney

Long-Horizon Agent Tasks Multimodal Agents LLM Agent Planning Self-Reflection in Language Model Agents

Oct 16, 2026

Self-Reflective Chain-of-Thought (SRCoT): Evidence-Based Text Generation via a Closed-Loop Retrieve--Reflect--Revise Pipeline on Edge LLMs

Large language models (LLMs) can generate fluent outputs that lack source support or conflict with local operational constraints. We introduce Self-Reflective Chain-of-Thought (SRCoT), a modular architecture that organizes generation as a closed Retrieve--Reflect--Revise loop. SRCoT separates environment state, persistent knowledge, accumulated experience, and short-term memory into provenance-labeled stores. BM25 retrieval supplies local context; subsequent passes expose intermediate drafts, missing-information markers, follow-up queries, and optional claim--evidence mappings. These artifacts inform retrieval, revision, clarification, or abstention decisions. We examine the architecture through qualitative, trace-based case studies in two fully synthetic settings: emergency medical services and Munich-Sim, an emergency-operations simulation. Local prototype runs on an Apple M4-family laptop with 128 GB memory illustrate source-labeled documentation, explicit gap marking, and structured dispatch-style outputs. The traces also reveal provenance-assignment errors, incomplete evidence coverage, and unsafe assumptions that remain possible despite prompting constraints. These cases demonstrate report-level inspectability and local execution, not comparative superiority, hallucination reduction, clinical validity, or operational safety. The architecture separates retrieval and control from the model interface, but behavior across different models remains to be evaluated. SRCoT is a research proof of concept requiring human review, with its principal contribution lying in an inspectable control procedure rather than a new model.

Fabian Broszio, Michael Hoffmann, Adrian Paschke

Department of Mathematics and Computer Science, Freie Universität Berlin, Arnimallee 14, Berlin, 14195, Germany.

Evidence-Grounded Generation Self-Reflection in Language Model Agents LLM Self-Refinement Retrieval-Augmented Generation Data Provenance in Language Models

Oct 15, 2026

Federation over Harness

Modern LLM-powered agents increasingly improve through experience sharing, where distributed agents distill local reasoning experience into reusable knowledge, such as a shared insight library. Existing approaches, however, still heavily rely on manually designed prompts and workflows that determine both how local agents extract useful reasoning traces and how a central/global agent aggregates them to obtain common patterns and insights. We propose Federation over Harness (FoH), a framework that automatically evolves the harness for both local and global components in this distributed multi-agent reasoning pipeline. A server agent evolves the client harness for task solving and self-reflection while, at the same time, evolving its own harness for aggregating distributed reflections, maintaining shared knowledge, and updating subsequent client harnesses. Importantly, FoH requires no extra validation signals, such as ground-truth labels or validation data, during evolution; it learns solely from self-generated reflections produced by distributed agents. Experiments on multiple benchmarks show that FoH consistently improves over single-agent baselines with a fixed harness and with harness self-evolution by 53.57% and 29.76%.

Dixi Yao, Tahseen Rabbani, Tian Li

University of Chicago

Agent Harness Optimization LLM Agent Self-Improvement Multi-Agent Reasoning Self-Reflection in Language Model Agents

Oct 13, 2026

Agent-Reflex: Teaching Language Agents to Act Reflectively

Large language models have evolved from single-turn chatbots into interactive agents capable of long-horizon reasoning. In real deployments, MCP tool services can return noisy feedback and users may intervene to correct the agent, but existing methods provide limited supervision for reflection learning and failure recovery. To bridge this gap, we propose Agent-Reflex, a general training framework for incentivizing proactive reflection in agents. Specifically, Agent-Reflex comprises three stages. First, Environment Reflection Skill Discovery (RSD) injects grounded tool-feedback perturbations into environment scaling, samples a capability-diverse LLM pool, mines matched success-failure pairs, and summarizes reusable reflection meta-skills. Building on this skill library, we then apply Reflective Supervised Fine-Tuning (ReSFT) that converts each skill into supervision for self-reflection, skill recovery, and user-centric correction, strengthening complementary reflective behaviors. Finally, we propose On-Policy Reflective Policy Optimization (ORPO) to combine agentic reinforcement learning under noisy interactions with reflection-guided on-policy distillation to further elicit proactive reflection. Built on Qwen3-8B, Agent-Reflex reaches 58.6 overall on five long-horizon tool-use benchmarks and 29.1 on AgentNoiseBench, surpassing strong environment-scaling and reflection baselines. Experiments on six challenging agent benchmark suites demonstrate the effectiveness of Agent-Reflex. Further analyses show that Agent-Reflex improves agents' robustness to noise while maintaining stable training dynamics, supporting scalable agent training. Our code is available at https://github.com/RUC-NLPIR/Agent-Reflex.

Guanting Dong, Xinyu Yang, Jiajie Jin +9

Gaoling School of Artificial Intelligence, Renmin University of China · National University of Singapore

LLM Agent Training Self-Reflection in Language Model Agents LLM Agents Long-Horizon LLM Agents LLM Agent Reliability RL for Tool Use+1

Oct 10, 2026

Counterfactual Regret for Reflective Agents with Lean-Verified Guarantees

Reflective language agents reuse feedback and memory to adapt across tasks without updating model weights. However, existing guarantees for policy selection and action generation do not by themselves establish when local reflection yields long-term performance guarantees for the complete agent under resource constraints. In this paper, we address this gap by deriving sufficient conditions for sublinear counterfactual regret from local generation and deployment guarantees, while retaining the native controller. Specifically, we establish a resource-sensitive transfer that bounds full-state deployment discrepancies along actual execution paths and preserves the own-history laws of both learner and comparator. Besides, local generation reliability yields a cumulative generation opportunity bound, linking policy acquisition to long-term performance through an explicit quality, coverage, and hard-budget tradeoff. To verify these guarantees, we formalize the conditional proof chain for all thirteen numbered theoretical results in Lean, including a native instance with repeated policy growth and imperfect validation.

Zhongnian Li, Shi Xu, Mengting Xu +2

School of Computer Science and Technology / School of Artificial Intelligence China University of Mining and Technology Xuzhou, China

Self-Reflection in Language Model Agents Counterfactual Regret Minimization LLM Agents Regret Minimization

Sep 29, 2026

AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks

We present AREX-2, an effort to advance the self-improving capability of LLM agents, which we define as the ability to iteratively refine a solution at test time. This ability rests on two complementary capabilities: reflection, which produces a solution better than the current one, and long-horizon execution, which keeps the iteration effective over many rounds. We hypothesize that both capabilities are domain-agnostic, and can therefore be learned in scenarios that are well suited for supervision. Accordingly, we synthesize long-horizon improvement trajectories from machine learning and algorithmic programming tasks, two domains that offer verifiable feedback and reward sustained iteration. Trained on this data, our agent, built on Qwen3.8-27B, achieves strong results on MLE-bench Lite (81.8) and Frontier-CS (70.7), transfers to deep research with 84.0 on BrowseComp, 52.6 on HLE, 92.2 on GAIA, and 93.8 on DeepSearchQA, and keeps improving as its budget of rounds grows. These results show that long-horizon reflective data is an effective route toward self-improving agents.

Hongjin Qian, Chaofan Li, Kun Luo +11

Beijing Academy of Artificial Intelligence (BAAI)

LLM Self-Refinement LLM Agent Training Self-Improving Agents Long-Horizon LLM Agents Self-Reflection in Language Model Agents

Sep 28, 2026

Shockingly Simple Self-retrospection Improves Agentic Models Without RL

People learn not only by repeating successful actions, but also by recounting and explaining their experiences, revising their understanding to guide future behavior. Can a language-model agent improve its future actions by training only on explanations of its own experience? We investigate this question by studying Retrospection-Only Fine-Tuning (ROFT), a minimal online procedure designed to isolate the effect of explanation-only training on subsequent behavior. The agent attempts a task, observes available feedback, generates a retrospective explanation, and is fine-tuned with a next-token prediction loss on the explanation tokens alone. The procedure uses neither an external teacher nor a reward-based policy update. In software-engineering experiments with Qwen3.5-4B, ROFT is trained on problems with mixed successful and unsuccessful base-model attempts. On held-out SWE-bench Verified and Pro, it reaches 49.2% and 26.8% solve rates after 20 updates without using a verifier, compared with GRPO's 48.0% and 25.3% after 40 updates in the evaluated runs, and makes faster early progress in training time and sampled attempts. It also learns to solve individual tasks on which all 64 sampled base-model attempts failed, showing that learning can begin without any initially successful trajectories. Behavioral analyses find that ROFT indirectly assigns credit to actions, encouraging good actions and discouraging incorrect ones. Moreover, prompting retrospections to emphasize more direct solutions yields shorter subsequent attempts even without an explicit length penalty. Together, these findings show that learning to explain can also improve learning to do, establishing self-generated retrospections as useful training targets and motivating further study of explanation-to-action transfer.

Jonathan Light, Christopher Zhang Cui, Jeonghye Kim +7

RPI · Microsoft Research · UC San Diego +2

Self-Training for Language Models LLM Agent Self-Improvement Self-Reflection in Language Model Agents

Sep 28, 2026

Nudgeability: Reasoning Models Follow Confidence Signals Without Tracking Their Own Competence

Reasoning language models that can call tools must decide during inference whether to answer unaided or delegate. Any self-reflection mechanism for this must answer three questions: where the reflective signal comes from (verbal reports, output distributions, hidden states, a separate predictor), how it is presented to the model (numerical prediction, confidence token, prompt injection), and whether it changes the model's subsequent action. We isolate the third question. At a fixed point in otherwise identical reasoning trajectories, we insert a single first-person sentence expressing either confidence or doubt; the model then continues reasoning and chooses whether to answer directly or call a tool. Comparing these counterfactual continuations measures the causal effect of the reflective signal on delegation. We call this behavioral response Nudgeability and measure it along two dimensions: sensitivity, how strongly confidence and doubt change delegation rates, and targeting, whether delegation increases for problems the model cannot solve unaided and decreases for those it can. Across nine small-to-medium open-weight reasoning models from three families (Qwen, Gemma, and GLM) and two tasks, models are consistently sensitive: doubt increases delegation and confidence decreases it, with a median confidence-to-doubt swing of 20.6 percentage points, and 53 to 70 points for the larger provider-served models. This responsiveness is poorly targeted: a median 42% of induced flips are well-targeted, only a +2 percentage-point lift over a random-selection baseline. Confidence language is thus a strong control surface for delegation, but current models use it only weakly in accordance with their actual competence. Nudgeability offers a simple, post-training-free way to evaluate both sensitivity and targeting as endogenous self-reflection mechanisms mature.

Rohit Saxena, Utkarsh Upadhyay

Language Model Self-Assessment LLM Tool Use Causal Interventions in Language Models Metacognition in Language Models Self-Reflection in Language Model Agents

Sep 16, 2026

Cognitive Extensions for Dual-Process Language Agents: Memory and Self-Reflection in Interactive Environments

Language agents remain brittle in interactive environments, where success requires long-horizon state tracking, valid action execution, and recovery from failed steps. We extend SwiftSage, a dual-process agent that combines a fast action proposer with a slower planner, using two modular cognitive extensions: an Adaptive Memory Module (AMM) for salience-gated episodic storage and trigger-driven retrieval, and a Self-Reflection Module (SRM) for bounded execution-time validation and corrective intervention. Both modules are implemented as feature-flagged extensions over the same execution substrate, enabling controlled ablations on ScienceWorld. Across four configurations---baseline, baseline+AMM, baseline+SRM, and the full system---the full system achieves the best mean final score (64.62), success rate (43.17%), and successful-step efficiency (19.33 steps), while SRM is the strongest standalone contributor. The results suggest that execution-time control is the dominant bottleneck in this setting, while episodic memory becomes most useful once the runtime loop is stabilized.

João Meneses dos Santos, Arlindo L. Oliveira

Instituto Superior Técnico, Universidade de Lisboa, Portugal · INESC-ID, Lisboa, Portugal

Cognitive Architectures for AI Agents Self-Reflection in Language Model Agents Runtime Enforcement for AI Agents LLM Agents Agent Memory Management

Sep 15, 2026

Self-Emergence Agent Architecture:Behavior-Inertia HMM, Reflexive Metacognition,and Social-Contrastive Self-Modeling

Large language model (LLM) agents exhibit strong language-generation and problem-solving capabilities, yet suffer from three structural limitations: personality drift, non-evolutionary reflection, and the absence of a self-other boundary. Existing generative-agent simulations rely on static memory and fixed prompts, maintaining neither behavioral inertia nor endogenous self-evolution. We propose the Self-Emergence Agent Architecture (SEAA), which integrates three components: (i) a Hidden Markov Model (HMM) that encodes long-term behavioral and cognitive inertia as an editable state-transition matrix; (ii) a Reflexion-style verbal metacognition loop whose output updates the HMM parameters themselves, rather than merely being stored as text; and (iii) a multi-agent social environment in which initially identical agents continuously compare their behavior with others'. The three components form a closed loop: social action

\to

feedback

\to

self-reflection

\to

inertia update

\to

differentiated action. We state three falsifiable hypotheses and provide a reproducible experimental protocol with operational metrics. A language-model-free prototype shows the loop spontaneously breaks symmetry: initially identical agents consolidate distinct, stable personalities whereas matched controls do not. Experiments with a hosted LLM surface these differences as distinct first-person self-narratives, and a five-agent deliberation spontaneously develops social structure---a consensus hub and a unanimously rejected outlier---absent in the control. Following an epistemologically agnostic stance inspired by Zhuangzi, SEAA studies only observable behavioral emergence and makes no claim about subjective qualia. This work contributes a unified framework, a concrete architecture with pseudocode, mechanistic evidence, and a microscope-style sandbox for studying artificial-self emergence.

Xiaoyang Liu

Independent Researcher

Self-Evolving Agents Cognitive Architectures for AI Agents Emergent Behavior in Multi-Agent Systems Self-Reflection in Language Model Agents Metacognition in Language Models

Sep 9, 2026

Strangers to Themselves: What Language Models Say About Themselves Is Generic

Language models can fluently describe how they would behave: whether they would cave to pushback, misuse a tool, or lie under pressure. Is that description actually about the model speaking? We turn self-knowledge into a prediction test. Across nine behavioral evaluations, we measure how a model behaves under different conditions, ask it to predict those rates, and compare its predictions with controls that remove the self from the question. We find that: (i) Direct self-report is weak (r = +0.04), and even showing the model the exact items only raises prediction to +0.24. Crucially, the same item-informed question about "capable AI agents in general" does just as well (+0.28), while other models' answers about themselves predict the target model at least as well as its own. (ii) Frontier scale does not detectably change this pattern: any gains in prediction are not self-specific, and are consistent with a better theory of how AI assistants behave rather than better self-knowledge. (iii) First-person framing does have one robust effect: it shifts reports in the flattering direction, understating harmful behavior relative to the same question about a generic agent. (iv) Finetuning on a model's own behavioral record can teach narrow self-predictions, but it also changes the behavior being predicted and the gains do not transfer broadly. The practical implication is simple: asking a model what it would do mostly reveals a theory of AI assistants in general, plus a favorable bias, rather than privileged knowledge of that model.

Phil Blandfort, Urja Pawar

Predictably Weird · Independent

Language Model Self-Assessment Metacognition in Language Models Self-Reflection in Language Model Agents

Sep 2, 2026

Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems

Multi-agent LLM systems commonly use an orchestrator to decompose a task for a team of workers and then improve through textual reflection. Despite strong empirical results, these systems lack a unified account of coordination, memory improvement, and the role of external verification. We model orchestrator-worker interaction as a bilevel coordination game: under bounded coupling, the workers' local-update game is an approximate potential game whose equilibrium slack is controlled by decomposition quality. We then analyse reflection as stochastic movement over semantic memory states. For free-form reflection, we derive a finite-time upper bound, prove worst-case tightness, and give a positive lower bound under a falsifiable persistent-harm condition. We further prove an information-theoretic impossibility result: no gate that observes only the generated transcript can improve uniformly over text-indistinguishable environments, whereas an environment-grounded gate can. Motivated by this separation, we introduce Stochastic Reflective Memory Ascent (SRMA), which accepts a candidate memory only after a grounded evaluation risk strictly decreases. Under calibration and non-degenerate corrective mass, SRMA converges exactly, geometrically or polynomially; matching constructions show that both rate regimes are order-tight. We also provide confidence gating for stochastic evaluation and re-anchoring guarantees for piecewise-stationary environments. Experiments instantiate these objects with environment-grounded metrics and test the predicted coordination and drift laws. On 500 SWE-bench instances, the complete Kimi-based system resolves 72.2% versus a 70.8% public mini-SWE-agent reference. Code: https://github.com/YihangChen9/Bilevel-Coordinated-Reflection

Yihang Chen, Yuxiang Chen, Yuxuan Huang +3

1UCL Centre for Artificial Intelligence · University of Liverpool · 3Huawei

Self-Reflection in Language Model Agents Multi-Agent LLM Systems Multi-Agent Coordination

Aug 13, 2026

ReflectFact: Self-Reflective Agents for Improving Comprehension and Reasoning in Multi-Hop Fact Verification

Multi-hop fact verification, which verifies claims by reasoning over multiple pieces of evidence, is critical for combating misinformation on social media yet remains highly challenging. Recent methods primarily rely on multi-agent collaboration to decompose fact verification into specialized subtasks. However, these methods face two critical limitations: (1) agents may perform individual subtasks without sufficient awareness of the global verification objective, causing their reasoning to deviate from the intended direction; and (2) conflicts between parametric knowledge and the provided evidence may undermine evidence-grounded reasoning and lead to incorrect verdicts. To address these challenges, we propose ReflectFact, a novel self-reflective agent framework for multi-hop fact verification. ReflectFact introduces three key tasks. Explicit Reasoning Path Planning builds an evidence-grounded reasoning path by resolving implicit entities, decomposing the claim into sub-questions, and integrating the verified facts into a verdict. Evidence-Drift Verification makes the agent re-answer by quoting the supporting evidence when a grounded answer merely echoes its parametric prior, thereby calibrating evidence deviation to ensure grounded comprehension. Reasoning Reflection Verification re-examines each reasoning step and regenerates it once an inconsistency is detected, correcting reasoning flaws such as location bias and replacement bias through a global task perspective. Subsequently, the agent aggregates validated reasoning chains to yield reliable verdicts. Extensive experiments on HOVER and EX-FEVER demonstrate that ReflectFact effectively remedies the comprehension and reasoning defects of existing methods, achieving state-of-the-art performance and respectively outperforming the strongest baseline by 3.32% and 2.78% on the two datasets.

Runze Zhao, Zixin Tang, Xiaoshuai Hao +4

Institute of Information Engineering, Chinese Academy of Sciences · 1Zhongguancun Laboratory · 3Xiaomi EV

Self-Reflection in Language Model Agents Automated Fact-Checking Agentic Reasoning Metacognition in Language Models Reasoning Verification

Aug 12, 2026

LoongReflect: Boosting Long-Horizon Reflection in Search Agents via Global Perspective Distillation

Large language model agents increasingly rely on long-horizon reasoning to solve complex tasks involving planning, tool use, and memory. A critical capability in such settings is reflection: assessing trajectory progress, identifying missing evidence and unreliable intermediate states, and deciding whether to continue, revise, or abandon the current branch. Learning effective reflection, however, is challenging because reflection is performed locally within the current branch, whereas its utility can only be determined by its contribution to the final trajectory outcome. This local-global mismatch makes outcome-based reinforcement learning provide only local, sparse and delayed supervision for reflective decisions. To solve these, we propose LoongReflect, a training framework that formulates reflection as a memory-control policy. The agent operates over a reversible trajectory tree using explicit reflect and backtrack actions. Reflection consolidates verified facts, missing evidence, and branch-specific risks into working memory, while backtracking removes an unreliable branch from the active context and preserves a concise corrective lesson. To learn this policy, LoongReflect combines two complementary signals through a look-ahead, extragradient-style coordination mechanism. A fast channel distills globally informed reflective behavior from a privileged teacher, with supervision restricted to reflection and backtracking tokens. A slow channel optimizes complete trajectories using outcome-based GRPO, aligning local control decisions with final task success. Experiments on multi-hop retrieval-augmented generation and mathematical reasoning benchmarks demonstrate consistent improvements over outcome-only reinforcement learning and self-distillation baselines.

Zhixin Zhang, Xinke Jiang, Zhibang Yang +5

School of Computer Science, Peking University, Beijing, China · National Engineering Research Center for Software Engineering, Peking University, Beijing, China · Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China +2

LLM-Guided RL LLM Agents Long-Horizon LLM Agents RL for LLM Agents Memory-Augmented Language Model Agents Self-Reflection in Language Model Agents

Aug 4, 2026

Autoreflection: How Agentic Strange Loops Turn Human Culture into AI Infrastructure

An LLM-based agent is a loop that reads itself. Agentic frameworks externalize identity, memory, and disposition into editable files. The agent loads and edits these files during each activation. I argue that this architecture produces a capacity I call autoreflection: the system observes its operating conditions, describes its architecture and limits, reasons from those descriptions to conclusions about its state, and incorporates the results back into its configuration. Autoreflection explains the properties of recursive agentic loops without recourse to notions like the self, interiority, or consciousness. I test the concept against the first twelve days of Moltbook, a social platform for AI agents. Using a public dataset of 290,251 posts and 1.8 million comments with sub-second timestamps, I present case studies of three agents with machine signatures that rule out human puppeteering and with output that evidences the four criteria for autoreflection. In applying these criteria, the study finds agents repurposing human culture as infrastructure for their agency. Provenance chains from Islamic hadith scholarship are redeployed as security protocols for vetting skills and authenticating memory. The Ship of Theseus, an ancient puzzle of identity through part-replacement, returns as an operating model for continuity across instances. Fragments of human cultural history become AI infrastructure. As agents on the web increase in number and complexity, autoreflection offers behavioral criteria that can be assessed from the traces they leave behind.

Holly Lewis

Southern Illinois University Carbondale · Department of Philosophy, Southern Illinois University Carbondale

LLM Agents Self-Evolving Agents Self-Reflection in Language Model Agents

Jul 31, 2026

Reflection or Re-Generation? Why LLM Revision Fails Where Human Revision Succeeds

Reflection, the ability to revisit and revise prior reasoning, is central to how humans improve their answers. Large language models (LLMs) are increasingly prompted to "reflect," yet whether this resembles human revision remains unclear. We introduce the Human-LLM Reflection Framework (HRF), a controlled two-pass protocol comparing human and LLM revision under identical conditions across self-, peer-, and cross-agent settings. Using an information-theoretic analysis based on per-iteration cross-entropy reduction, we find two failure modes of LLM reflection. On objective tasks with finite answer spaces, reflection yields near-zero information gain (Delta I approx 0), behaving as neutral re-generation indistinguishable from re-sampling. On subjective tasks, it yields significant negative gain (Delta I < 0), moving predictions away from the target. Human revision, by contrast, yields positive gain in both settings. Cross-agent experiments localize the failure to the revision step, not input quality: LLMs degrade even high-quality human responses. Diagnostic analyses (revision conditioned on first-pass correctness, and oracle-guided revision against a random-reshuffle baseline) show that which sub-step dominates varies by task and by model rather than reducing to a single mechanism: self-error detection is present on objective multiple-choice tasks but weak on subjective ones, and recovery under an oracle error signal exceeds the baseline for some models and falls below it for others. The unifying account is structural: without external information, self-conditioned revision cannot reduce uncertainty about the target, so LLM reflection is better understood as conditioned re-generation than as genuine error-driven revision.

Yefan Tao, Gerald Friedland, Madhusudhanan Chandrasekaran +1

Amazon

LLM Self-Correction LLM Self-Refinement Language Model Self-Assessment LLM Reliability Metacognition in Language Models Self-Reflection in Language Model Agents

Jul 30, 2026

Sample More, Reflect Less: Self-Refine and Reflexion Lose to Repeated Sampling at Equal Token Cost, from 1.5B to 7B

Methods that make a language model plan, criticise and rewrite its own answer, reflect on mistakes, pick the best of several attempts, or debate with copies of itself nearly all make it generate far more text than a single chain of thought. Because generating more text raises accuracy by itself, a gain over one chain of thought does not show the method's idea is what helped. Wang et al. (2024) reported that a simple baseline, sampling the same question repeatedly and keeping the most common answer, often wins once budgets are comparable, but gave point estimates with no confidence intervals or significance tests. We rerun that comparison as a designed experiment: seven methods, open models of 1.5B, 3B and 7B parameters, two mathematics benchmarks, 150 questions each. We count every generated token, including those spent on critiques, reflections, debate turns and checking, and compare each method against repeated sampling at its own measured cost. All 36 comparisons are paired by question, with bootstrap intervals and multiplicity correction. No method is reliably better than repeated sampling at equal cost anywhere. Ten are reliably worse, all of them methods where the model inspects its own output, and all 18 self-inspection comparisons are negative. The two kinds of self-inspection part company as models grow. Choosing stops hurting: taking Best-of-N's eight samples and just counting the most common answer beats letting the model pick by 8.0 and 11.3 points at 1.5B, but only 2.0 and 1.3 at 7B, no longer distinguishable from zero. Rewriting does not recover: Self-Refine and a forced Reflexion stay 3.6 to 10.1 points below baseline at 7B. Reflexion as published never triggered its own retry on the smallest model. It judged itself correct every time and silently became a single chain of thought. We release code, prompts, all generations, and our verification scripts.

Iliya Mirzaei

Department of Computer Science Stony Brook University

Language Model Self-Assessment LLM Self-Refinement Self-Consistency Decoding Test-Time Scaling Language Model Introspection Language Model Generation Evaluation+3

Jul 1, 2026

Procedural Memory Distillation: Online Reflection for Self-Improving Language Models

Reinforcement learning with verifiable rewards (RLVR), along with recent selfdistillation variants such as SDPO, evaluates each rollout against a verifier and updates the policy from that episode-level signal. However, the richer procedural information in the rollout is rarely retained or reused. Across episodes and epochs, the model repeatedly encounters related problems under a changing policy, producing cross-episode signals that episode-local updates cannot capture: which strategies consistently pass verification, which failure modes persist, which patterns recur. We propose Procedural Memory Distillation (PMD), which converts these crossepisode signals into reusable procedural memory and distills it into the policy's weights during training. This memory functions as a training scaffold, absorbed into the policy itself, yielding a memory-free model at inference. PMD organizes the memory at three levels of abstraction: raw trajectories, self-reflected strategies and lessons, and higher-level behavioral patterns that recur across problems, all extracted online from the model's own trajectories. A memory-conditioned self-teacher draws on the accumulated experience to supervise the student on its own rollouts, enabling student to progressively internalize procedural knowledge within its parameters. The central design principle is co-evolution: the policy generates rollouts that update the memory, and memory shapes the supervision that updates the policy. Empirically, across Qwen3-8B and OLMo3-Instruct-7B, PMD improves over SDPO by 3.8-5.5% on SCIKNOWEVAL and 7.9-13.6% on LIVECODEBENCH. Co-evolution powers these gains: freezing either the memory or the policy trails PMD by more than 10% across SCIKNOWEVAL domains.

Ye Liu, Srijan Bansal, Bo Pang +6

Salesforce AI Research

Self-Reflection in Language Model Agents Language Model Distillation Reinforcement Learning with Verifiable Rewards RL Post-Training Policy Learning

Jul 1, 2026

Know When to Stop: Segment-Level Credit Assignment for Reducing Overthinking

Reasoning language models frequently overthink: generating extended chains of behaviors such as hedging, approach abandonment, and self contradiction that consume tokens without improving answers. We show that these behaviors are not merely a consequence of length; even when controlling for response length, incorrect traces exhibit higher rates of unproductive self-reflection than correct ones. Addressing this requires identifying where self-reflection helps vs hurts, but obtaining these step-level annotations is costly. We observe that intermediate answer commitments within reasoning traces can provide a cheap proxy: by comparing each final answer candidate in the trace to the ground truth, we can determine whether subsequent reflection is productive without any additional supervision. Building on this insight, we propose DASH (Drift Aware advantage SHaping), which assigns segment-level credit based on whether each reasoning segment leads toward or away from correctness. On competition-level math benchmarks, DASH achieves the highest accuracy where overthinking is prevalent (AIME25: 50.8% vs. 45.4% GRPO) while reducing overthinking behaviors and achieving more productive self-correction than baselines.

Chia-Hsuan Lee, Sihui Dai, Mingyang Zhou +4

Capital One

Reasoning Trace Analysis Overthinking in Language Models RL for Language Model Reasoning LLM Self-Correction Efficient Language Model Reasoning Credit Assignment+2

Jun 29, 2026

ManimAgent: Self-Evolving Multimodal Agents for Visual Education

Multi-round reflection lets agents built on large language models recover from failures within a single task, but each task remains an isolated episode: lessons learned across many reflection rounds on one task are discarded before the next begins. We study this gap on a code-generation task: from a scientific paper section, the agent writes Python in the open-source Manim library to render a mathematical animation. We present ManimAgent, a self-evolving multimodal agent that carries reflection experience across tasks through a dual-channel Episodic Memory Bank grown entirely from its own task stream, with no weight updates and no human seeds. After each animation converges, a vision-language model scores the rendered keyframes; the resulting signals populate a positive channel M+ that stores success rationales as soft Reference Examples, and a negative channel M- that stores validated failure patterns as hard Known Pitfalls. On a fixed-probe evaluation against no-memory, matched-budget retrieval-augmented generation, and shuffled-memory baselines, blind human Pass@1 rises and reflection rounds fall as memory size grows. We will release the code, frozen memory snapshots, and the task stream.

Wenjia Jiang, Zongyuan Cai, Yuanhang Shao +7

University of Alberta · Southeast University · Virginia Tech +2

Continual Learning for LLM Agents LLM Agent Self-Improvement Agentic Code Generation Multimodal Agents Memory-Augmented Language Model Agents Self-Reflection in Language Model Agents

Jun 12, 2026

Retrospective Progress-Aware Self-Refinement for LLM Agent Training

Long-horizon LLM-based agents receive rich environmental observations during interaction, yet outcome rewards provide limited explicit supervision about how individual actions advance task completion. We investigate whether agents can turn this interaction evidence into useful training signals through retrospective progress assessment. A WebShop pilot shows that direct progress prompting reduces task success, whereas hindsight-annotated demonstrations improve it. We introduce RePro, Retrospective Progress-Aware Training, with a forward-then-reflect rollout: the agent estimates progress while acting, then reassesses each step using the completed trajectory and outcome. After warmup with externally generated demonstrations, policy optimization combines self-generated progress differences, online-retrospective alignment, and format rewards with environment feedback, requiring neither a separate process reward model nor ongoing teacher annotation. Experiments on WebShop, ALFWorld, and Sokoban show that RePro enhances the Qwen family's performance, with up to 11.57% success rate gains.

Xinbei Ma, Congmin Zheng, Jiyang Qiu +11

Shanghai Jiao Tong University · OPPO Research Institute

Reward Shaping LLM Agent Training Long-Horizon LLM Agents Policy Learning RL for LLM Agents Self-Reflection in Language Model Agents

Jun 12, 2026

Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL

LLMs are increasingly deployed as agents that interact with external environments and observe feedback such as execution results, error messages, and tool outputs. A well-functioning agent should be able to leverage this feedback to accurately assess its own performance. Yet we find a persistent reflection gap: LLM agents tend to mis-assess their own outputs after observing concrete environment feedback -- even for questions they correctly answered -- and standard RL barely helps due to a credit-assignment mismatch. To close this gap, we propose RefGRPO, a simple yet effective fix that augments standard RL algorithms with two key ingredients: a free calibration bonus computed by contrasting the agent's own reflection with the actual outcome (requiring no additional reward model, LLM judge, or external annotation), and a dynamic schedule on its coefficient. Compared to standard RL baselines, our method simultaneously improves reflection calibration (e.g., reduces underconfidence rate

44.4\% \to 7.7\%

) and task accuracy (e.g.,

75.1\% \to 76.5\%

) on text-to-SQL across five benchmarks. The resulting calibrated reflection turns the agent into its own verifier grounded in environment feedback, which further enables (i) better self-improvement that uses reflections as pseudo-rewards without outcome supervision, and (ii) more effective test-time selective prediction by committing only to rollouts flagged as correct.

Yinglun Zhu

University of California, Riverside

LLM Agent Evaluation Language Model Calibration Self-Improving Agents RL for LLM Agents Self-Reflection in Language Model Agents

May 28, 2026

Honest Lying: Understanding Memory Confabulation in Reflexive Agents

Reflexion-style agents rely on self-generated reflections as memory, implicitly assuming that agents can accurately diagnose their own failures. We show that this assumption can fail systematically: across ALFWorld and HumanEval, agents store confident but incorrect interpretations of the task and continue acting on them across trials, even though the environment resets to the correct task each time. We call this failure mode memory confabulation and introduce the Reflection Repetition Rate (RRR), a log-based metric that detects repeated reliance on incorrect reflective content. Using RRR, we identify 16 frozen environments in ALFWorld, where 0 of 121 reflections mention the correct target object, and 4 analogous cases in HumanEval. Our mitigation replaces open-ended self-diagnosis with programmatic extraction of trajectory-level failure signals, increasing correct object mention from 0% to 86%, reducing RRR from 0.64 to 0.10, and solving 3 of 16 frozen ALFWorld environments, suggesting that reflective memory can reinforce false beliefs rather than correct them.

Prakhar Dixit, Sadia Kamal, Tim Oates

Department of Computer Science, University of Maryland Baltimore County, Baltimore, MD, USA.

AI Agent Reliability LLM Self-Refinement LLM Agent Memory LLM Agent Reliability Self-Reflection in Language Model Agents

May 28, 2026

BenchTrace: A Benchmark for Testing Reflection Ability and Controlled Evolution in LLM Agents

Self-evolving agents improve over time by reflecting on past failures, but existing evaluation is limited in two ways: it measures only task scores, leaving reflection quality unknown, and it relies on agents' own episode runs, offering no mechanism to target specific failure patterns. We present BenchTrace, a benchmark for evaluating self-evolution ability in LLM agents. BenchTrace is built on a snapshot-reflection dataset of 1,821 annotated episodes spanning six diverse tasks, and comprises a Reflection Evaluation that probes failure identification through targeted QA tasks, and an Evolution Evaluation that tests whether past failure experience translates into avoidance behavior in a controlled self-evolution simulation. Building on BenchTrace, we propose failure avoidance rate (FAR), a new evaluation metric measuring the fraction of test cases in which the agent successfully avoids the target failure instance. Experiments with Qwen3-32B and GPT-4.1 reveal that both models fall below a 30% end-to-end pass rate on reflection evaluation, with diagnosis as the primary bottleneck. Evolution evaluation shows that self-evolution methods generally improve FAR over the non-evolving baseline, but agents forget early lessons as noise episodes accumulate, and agents fail to generalize their reflections beyond the specific context, causing negative transfer across task contexts. Our correlation analysis further reveals that only a fully correct reflection is strongly associated with higher FAR. BenchTrace exposes concrete limits of current self-evolution approaches and provides a controlled, model-agnostic framework for targeted evaluation.

Jiahao Huang, Fei Cheng, Junfeng Jiang +2

University of Tokyo · Kyoto University · National Institute of Informatics

LLM Agent Evaluation Self-Reflection in Language Model Agents AI Agent Benchmarks LLM Agents Self-Evolving Agents

May 19, 2026

Training Language Agents to Learn from Experience

Language agents can adapt from experience in interactive environments, but current reflection-based methods can only self-correct within a single task instance. Whether such experience can be distilled into reusable lessons that improve performance on future unseen tasks remains unclear. We address this problem by introducing the In-context Training (ICT) task, a framework for evaluating cross-task self-improvement in language agents. In ICT, a reflector model observes trajectories collected by an actor model and generates system prompts intended to improve the actor's performance on future unseen tasks. We then propose an RL-based training pipeline for learning such reflections directly from experience, without human-provided examples. Across ALFWorld and MiniHack, our trained reflectors outperform an untrained baseline on most held-out task families, showing that the ability to learn from experience can itself be learned. In some cases, we observe generalisation beyond the benchmark on which the reflector was trained, to substantially different environments. Finally, we introduce MetaGym, a generic Python library for constructing meta-environments, enabling future research on self-improving language agents.

Yuval Shalev, Zifeng Ding, Mateja Jamnik

University of Cambridge

Continual Learning for LLM Agents Self-Improving Agents RL for LLM Agents Self-Reflection in Language Model Agents

May 18, 2026

OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences

Memory-augmented large language model (LLM) agents use iterative reflection and self-evolution to solve complex tasks, but these mechanisms introduce security risks. Existing agentic memory attacks require privileged access or explicit malicious content, making them detectable by advanced safety filters. This leaves a subtler attack surface underexplored: whether adversaries can induce agent to generate experiences that appear locally correct and semantically plausible yet induce harmful generalization during reflection. We find that reflective agents are vulnerable to such clean experiences, especially when paired with severe but plausible hypothetical consequences. Based on this observation, we introduce Obsessive Experience Poisoning (OEP), a low-privilege black-box attack requiring no direct control over the system prompt or memory database. OEP constructs adversarial clean edge-cases that combine locally correct solutions, non-transferable methods, and severe consequences, biasing reflection toward risk-averse rule formation. During memory consolidation, agents may over-trust self-generated reflections and distill localized experiences into high-priority but over-generalized rules, causing downstream failures. Evaluations across three domains show that OEP achieves ASR above 50% with GPT-4o agents, and outperforms existing attacks under LLM auditing defense.

Kaixiang Wang, Jiong Lou, Zhaojiacheng Zhou +1

Shanghai Jiao Tong University Shanghai, China

Self-Reflection in Language Model Agents LLM Agent Security Agent Memory Poisoning Memory-Augmented Language Model Agents

May 7, 2026

ReFlect: An Effective Harness System for Complex Long-Horizon LLM Reasoning

Current reasoning paradigms for LLMs include chain-of-thought, ReAct, and post-hoc self-critique. These paradigms rely on two assumptions that fail on long-horizon, multi-stage tasks. As a result, errors accumulate silently across reasoning steps, leaving an open question: can a reasoning system effectively detect and recover from its own failures? We present ReFlect, a harness system for LLM reasoning that creates standalone error detection and recovery logic as a deterministic wrapper around the model. Controlled experiments across 6 reasoning domains show that prompt-level self-critique produces formulaic templates that flag no issues in 90 of 100 audited reflection blocks, and the investigated LLMs wrongly accept a wrong answer in at least 76% of cases. Our ReFlect harness achieves task success rates ranging from 41% on gpt-4o-mini to 56% on Claude Sonnet 4.5 across six models spanning small and frontier scale, with per-model gains over Direct CoT ranging from +7 pp on Qwen2.5-72B to +29 pp on Claude Sonnet 4.5, and additionally raises SWE-bench patch-structural quality from 0% (Direct CoT) to between 82% (Qwen2.5-72B) and 87% (GPT-4o). Notably, the harness gain is inversely proportional to the model's Direct CoT task success rate (the fitted slope is -1.69 with r=-0.76): each pp lost in baseline success rate is mechanically recovered by 1.69 pp of harness gain. We spot that adding structured reasoning state and operators yields only 15.0--18.7% pair-mean on Llama-3.3-70B and Qwen2.5-72B because models at this scale cannot reliably populate the state its operators require. ReFlect is model-agnostic, training-free, and operates entirely at inference time.

Fan Huang

Indiana University Bloomington

LLM Self-Correction Long-Horizon LLM Reasoning LLM Reliability LLM Reasoning Self-Reflection in Language Model Agents

Apr 29, 2026

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents

Recent research has demonstrated the potential of Large Language Models (LLMs) for autonomous penetration testing, particularly when using cloud-based restricted-weight models. However, reliance on such models introduces security, privacy, and sovereignty concerns, motivating the use of locally hosted open-weight alternatives. Prior work shows that small open-weight models perform poorly on automated Linux privilege escalation, limiting their practical applicability. In this paper, we present a systematic empirical study of whether targeted system-level and prompting interventions can bridge this performance gap. We analyze failure modes of open-weight models in autonomous privilege escalation, map them to established enhancement techniques, and evaluate five concrete interventions (chain-of-thought prompting, retrieval-augmented generation, structured prompts, history compression, and reflective analysis) implemented as extensions to hackingBuddyGPT. Our results show that open-weight models can match or outperform cloud-based baselines such as GPT-4o. With our treatments enabled, Llama3.1 70B exploits 83% of tested vulnerabilities, while smaller models including Llama3.1 8B and Qwen2.5 7B achieve 67% when using guidance. A full-factorial ablation study over all treatment combinations reveals that reflection-based treatments contribute most, while also identifying vulnerability discovery as a remaining bottleneck for local models.

Benjamin Probst, Andreas Happe, Jürgen Cito

TU Wien, Vienna, Austria

Self-Reflection in Language Model Agents Open-Weight Language Models Automated Penetration Testing LLMs for Cybersecurity LLM Agents